Works with the AI Agents you already use
SLR: Systematic Literature Review (PRISMA 2020)
A skill that guides you through a Systematic Literature Review (SLR), from research question to the methodology section.
Free
SLR: Systematic Literature Review (PRISMA 2020)
Example session with this skill installed
I have 165 records from Scopus and 126 from WoS. After de-duplication, I have 180 unique records. 160 were excluded at title/abstract. Can you generate the PRISMA 2020 counts and flow logic?
- Read your context and instructions
- Compiled the slr
I have processed the screening numbers provided. I have mapped these to the PRISMA 2020 requirements and verified the arithmetic logic.
PRISMA 2020 Screening Results
| PRISMA Phase | Item | Count |
|---|---|---|
| Identification | Records identified from Scopus | 165 |
| Records identified from Web of Science | 126 | |
| Total records identified | 291 | |
| Duplicates removed | 111 | |
| Screening | Records screened (Title/Abstract) | 180 |
| Records excluded | 160 | |
| Eligibility | Reports sought for retrieval | 20 |
| Reports not retrieved | 0 | |
| Reports assessed for full-text eligibility | 20 | |
| Reports excluded with reasons | Pending | |
| Included | Total studies included in review | 20 (Preliminary) |
Arithmetic Verification
- Identification Check: 291 total records minus 111 duplicates equals 180 records for screening. [OK]
- Screening Check: 180 screened minus 160 excluded equals 20 reports sought for retrieval. [OK]
- Eligibility Check: 20 assessed minus 0 excluded (at this stage) equals 20 included. [OK]
Next steps
1.
Full-Text Review: Upload the full-text screening log to categorize the final exclusion reasons (e.g., wrong population, not empirical).
2. Evidence Table: Provide the citations for the 20 included papers to begin the data extraction phase.
3. Methodology Draft: Request a draft of section 2.1.3 (Study Selection) once final exclusion reasons are coded.
Connects securely to your tools. The creator never sees your data.
About this skill
A skill that guides you through a Systematic Literature Review (SLR), from research question to the methodology section. It works for any discipline that needs a transparent, reproducible review.
What it covers
- Research question and inclusion/exclusion criteria, with a justification for each
- Search strings per database (Scopus, Web of Science, PubMed, IEEE and others) with syntax notes
- A title/abstract screening protocol: blind dual review, Include / Exclude / Maybe codes, coded exclusion reasons, a pilot round, 90% agreement plus Cohen's kappa
- A cross-check protocol for a team's screening sheet: IDs, decisions, reasons, criteria versus data, query versus counts, PRISMA arithmetic
- PRISMA 2020 flow numbers with arithmetic checks
- Evidence table, concept matrix, codebook, and open / axial / selective coding
- A methodology-section template and a QA checklist
What is inside
- SKILL.md with the full method
- An Excel screening workbook: protocol, search log, records, two-reviewer screening, reliability, PRISMA counts with OK / MISMATCH checks, a formula-driven PRISMA flow diagram, evidence table, concept matrix and logbook
- A Python script that regenerates the workbook
Method
It combines Wolfswinkel, Furtmueller & Wilderom (2013) for the process, PRISMA 2020 and PRISMA-S for reporting, and Gioia et al. (2013) for coding.
What it does not do
It cannot search Scopus or Web of Science for you; those need your licence. You run the string, export the results and hand them over. The skill never invents papers, counts or dates: every PRISMA number comes from your own exports and logs. It does not replace your supervisor or a librarian, and you should check references and numbers before you submit.
Also free and open source (MIT) on GitHub: https://github.com/IBK015/claude-slr-skill
Requires user-provided search exports. Cannot access paywalled databases (Scopus/WoS) directly. Best suited for narrative and thematic reviews rather than quantitative meta-analysis.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 2 days ago
- Free with an Agensi account